
Reframes experience-learning from post-hoc trajectory summaries to explicit predictions anchored to state, which generalizes better and lets accumulated knowledge bootstrap rather than encode one lucky path.
articleSkillBoostHongqiang Lin, Chao Liu, Xiaofan Bai, Xuan Jin, Yuhong Li, Nenggan Zheng, Xipeng Cao
articleRethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple RoundsYuxuan Liu, Zhaochen Su, Yuhao Zhang, Jiahe Guo, Zhongwei Xie, Huihao Jing, Lingyun Xie, Qing Zong, Yauwai Yim, Zhixiong Zhang, Haoran Li, Yangqiu SongChecking sign-in…
Loading comments…